I’m first trying to replicate the image autoencoder, where the input and output image are different.
Here is my code.
"""
Dependencies:
torch: 0.4
matplotlib
numpy
"""
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm
import numpy as np
import pandas as pd
from barbar import Bar
# torch.manual_seed(1) # reproducible
# Hyper Parameters
EPOCH = 10
BATCH_SIZE = 256
LR = 0.005 # learning rate
DOWNLOAD_MNIST = False
N_TEST_IMG = 5
# Mnist digits dataset
class MyDataset():
def __init__(self, image_paths):
self.image_paths = image_paths
def __getitem__(self, index):
image, image_transformed = load_image(self.image_paths[index])
# transformations, e.g. Random Crop etc.
# Make sure to perform the same transformations on image and target
# Here is a small example: https://discuss.pytorch.org/t/torchvision-transfors-how-to-perform-identical-transform-on-both-image-and-target/10606/7?u=ptrblck
x, y = TF.to_tensor(image), TF.to_tensor(image_transformed)
return x, y
def __len__(self):
return len(self.image_paths)
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
# Data Loader for easy mini-batch return in training, the image batch shape will be (50, 1, 28, 28)
trainDataSet=MyDataset("./train.csv")
testDataSet=MyDataset("./test.csv")
train_loader = Data.DataLoader(trainDataSet, batch_size=BATCH_SIZE, shuffle=True)
test_loader = Data.DataLoader(testDataSet, batch_size=BATCH_SIZE, shuffle=True)
class Autoencoder(nn.Module):
def __init__(self):
super(Autoencoder,self).__init__()
self.encoder = nn.Sequential(
nn.Conv2d(3, 6, kernel_size=5),
nn.ReLU(True),
nn.Conv2d(6,16,kernel_size=5),
nn.ReLU(True))
self.decoder = nn.Sequential(
nn.ConvTranspose2d(16,6,kernel_size=5),
nn.ReLU(True),
nn.ConvTranspose2d(6,3,kernel_size=5),
nn.ReLU(True))
def forward(self,x):
x = self.encoder(x)
x = self.decoder(x)
return x
autoencoder = Autoencoder()
autoencoder.to(device)
print(autoencoder)
optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR)
loss_func = nn.MSELoss()
df = pd.DataFrame({'Epoch':[],'Train': [],
'Test':[]})
count = 1
for epoch in range(EPOCH):
for step, (x, y) in enumerate(train_loader):
autoencoder.train()
running_loss = 0.0
b_x = x.view(-1, 750*750).to(device) # batch x, shape (batch, 28*28)
b_y = y.view(-1, 900*800).to(device) # batch y, shape (batch, 28*28)
encoded, decoded = autoencoder(b_x)
loss = loss_func(decoded, b_y) # mean square error
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
running_loss += loss.item()
if step % 100 == 0:
for step, (x, b_label) in enumerate(test_loader):
autoencoder.eval()
test_loss = 0.0
b_x = x.view(-1, 750*750).to(device) # batch x, shape (batch, 28*28)
b_y = x.view(-1, 900*800).to(device) # batch y, shape (batch, 28*28)
encoded, decoded = autoencoder(b_x)
loss = loss_func(decoded, b_y) # mean square error
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
test_loss += loss.item()
print('Epoch: ', epoch + 1, '| train loss: %.4f' % running_loss, '| test loss: %.4f' % test_loss)
df.loc[count] = [epoch + 1,running_loss, test_loss]
count = count + 1
torch.save(autoencoder.state_dict(), "./model.pt")
df.to_csv("./train-test-loss.csv", index = False)
However, I’m getting the error with the Dataset loader.
Autoencoder(
(encoder): Sequential(
(0): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
(3): ReLU(inplace=True)
)
(decoder): Sequential(
(0): ConvTranspose2d(16, 6, kernel_size=(5, 5), stride=(1, 1))
(1): ReLU(inplace=True)
(2): ConvTranspose2d(6, 3, kernel_size=(5, 5), stride=(1, 1))
(3): ReLU(inplace=True)
)
)
Traceback (most recent call last):
File "train_depth_map.py", line 92, in <module>
for step, (x, y) in enumerate(train_loader):
File "C:\Users\Username\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 363, in __next__
data = self._next_data()
File "C:\Users\Username\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 403, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "C:\Users\Username\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "C:\Users\Username\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in <listcomp>
data = [self.dataset[idx] for idx in possibly_batched_index]
File "train_depth_map.py", line 38, in __getitem__
image, image_transformed = load_image(self.image_paths[index])
NameError: name 'load_image' is not defined
I’m currently unsure about why the Dataset is creating the issue. It seems like it load into the Dataloader, but an error seems to be having in the main train loop. I tried adapting this example, which was originally for cifar, but it appears that the Dataset is not load the images properly. I also had to remove Dataset from class MyDataset(Dataset):, since I was getting errors that it would not defined.
